paper-with-me

홈 › Papers

AuTAgent: A Reinforcement Learning Framework for Tool-Augmented Audio Reasoning

2026-02-14 · Siqian Tong, Xuan Li, Yiwei Wang, Baolong Bi, Yujun Cai, Shenghua Liu, Yuchen He, Chengpeng Hao arxiv

Large Audio Language Models (LALMs) excel at perception but struggle with complex reasoning requiring precise acoustic measurements. While external tools can extract fine-grained features like exact tempo or pitch, effective integration remains challenging: naively using all tools causes information overload, while prompt-based selection fails to assess context-dependent utility. To address this, we propose AuTAgent (Audio Tool Agent), a reinforcement learning framework that learns when and which tools to invoke. By employing a sparse-feedback training strategy with a novel Differential Reward mechanism, the agent learns to filter out irrelevant tools and invokes external assistance only when it yields a net performance gain over the base model. Experimental results confirm that AuTAgent complements the representation bottleneck of LALMs by providing verifiable acoustic evidence. It improves accuracy by 4.20% / 6.20% and 9.80% / 8.00% for open-source and closed-source backbones on the MMAU Test-mini and the MMAR benchmarks, respectively. In addition, further experiments demonstrate exceptional transferability. We highlight the complementary role of external tools in augmenting audio model reasoning.

📄 PDF Abstract BibTeX arXiv:2602.13685

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

EChO-Agent: Evidence Chain Orchestration Agent for Audio Reasoning

2026-06-13 · Siyuan Zhang, Jian Zong, Junyu Wang, Peiyuan Jiang 외 arxiv

While LALMs show promise on audio question answering, they fail to focus on question-relevant segments of audio and provide a clear, checkable reasoning process when dealing with complex audio reasoning. Reinforcement le…

Reinforcement LearningQuestion Answering

Audio-Maestro: Enhancing Large Audio-Language Models with Tool-Augmented Reasoning

2025-10-13 · Kuan-Yi Lee, Tsung-En Lin, Hung-Yi Lee arxiv

Recent advancements in large multimodal models (LMMs) have shown strong capabilities in audio understanding. However, most systems rely solely on end-to-end reasoning, limiting interpretability and accuracy for tasks tha…

Step-Audio 2 Technical Report

2025-07-22 · Boyong Wu, Chao Yan, Chen Hu, Cheng Yi 외 arxiv

This paper presents Step-Audio 2, an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation. By integrating a latent audio encoder and reasoning-centric rei…

Reinforcement LearningSpeech Recognition

AudioRouter: Data Efficient Audio Understanding via RL based Dual Reasoning

2026-02-11 · Liyang Chen, Hongkai Chen, Yujun Cai, Sifan Li 외 arxiv

Large Audio Language Models (LALMs) have demonstrated strong capabilities in audio understanding and reasoning. However, their performance on fine grained auditory perception remains unreliable, and existing approaches l…

Reinforcement LearningDecision Making

Rethinking Reinforcement Fine-Tuning in LVLM: Convergence, Reward Decomposition, and Generalization

2026-04-21 · Carter Adams, Rafael Oliveira, Gabriel Almeida, Sofia Torres arxiv

Reinforcement fine-tuning with verifiable rewards (RLVR) has emerged as a powerful paradigm for equipping large vision-language models (LVLMs) with agentic capabilities such as tool use and multi-step reasoning. Despite …